SSearch
Free web search for AI agents. No API key required. Hosted MCP in active development.
使うべきか
品質と安全性
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"search": {
"url": "https://api.ssearch.cc/mcp"
}
}
}リモートエンドポイント
https://api.ssearch.cc/mcpstreamable-httpできること
ツール一覧
ツール（7）
🟡search_web(query, max_results, fresh, wait_for_coverage)
Search SSearch. Set wait_for_coverage to search owned documents and, only if needed, external discovery on a miss.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
},
"max_results": {
"default": 10,
"title": "Max Results",
"type": "integer"
},
"fresh": {
"default": false,
"title": "Fresh",
"type": "boolean"
},
"wait_for_coverage": {
"default": false,
"title": "Wait For Coverage",
"type": "boolean"
}
},
"required": [
"query"
],
"title": "search_webArguments"
}🟢search_documents(query, max_results, promote)
Search SSearch-owned stored full-text documents. Successful misses can be promoted into the live index.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
},
"max_results": {
"default": 10,
"title": "Max Results",
"type": "integer"
},
"promote": {
"default": true,
"title": "Promote",
"type": "boolean"
}
},
"required": [
"query"
],
"title": "search_documentsArguments"
}🟢get_context(document_id, query, max_chars, max_passages)
Retrieve only the stored passages in a search result that are relevant to the information you need.
入力スキーマ
{
"type": "object",
"properties": {
"document_id": {
"title": "Document Id",
"type": "string"
},
"query": {
"title": "Query",
"type": "string"
},
"max_chars": {
"default": 5000,
"title": "Max Chars",
"type": "integer"
},
"max_passages": {
"default": 5,
"title": "Max Passages",
"type": "integer"
}
},
"required": [
"document_id",
"query"
],
"title": "get_contextArguments"
}🟢get_document(document_id, max_chars)
Retrieve the broader stored text for a known SSearch document ID.
入力スキーマ
{
"type": "object",
"properties": {
"document_id": {
"title": "Document Id",
"type": "string"
},
"max_chars": {
"default": 30000,
"title": "Max Chars",
"type": "integer"
}
},
"required": [
"document_id"
],
"title": "get_documentArguments"
}🟢fetch_page(url, archive_fallback, max_chars)
Fetch and extract readable page text; optionally fall back to Common Crawl.
入力スキーマ
{
"type": "object",
"properties": {
"url": {
"title": "Url",
"type": "string"
},
"archive_fallback": {
"default": true,
"title": "Archive Fallback",
"type": "boolean"
},
"max_chars": {
"default": 30000,
"title": "Max Chars",
"type": "integer"
}
},
"required": [
"url"
],
"title": "fetch_pageArguments"
}🟢search_plan(query)
Show the normalized local search plan for a query.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
}
},
"required": [
"query"
],
"title": "search_planArguments"
}🟢search_sources
Describe the local SSearch corpus and search backends.
入力スキーマ
{
"type": "object",
"properties": {},
"title": "search_sourcesArguments"
}推奨プロンプト
search_webget_contextsearch_webget_contextsearch_webget_contextコミュニティ
エビデンス